Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4096 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.1066. Min Range: -2.1066

Max Act: 2.1066. Min Act: -0.0000

Data Index: 890178 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 2.1066. Min Range: -2.1066

Max Act: 1.9795. Min Act: -0.0000

Data Index: 436988 (C4 (Web Text))

Max Activating Token Index: 603

Text #2

Max Range: 2.1066. Min Range: -2.1066

Max Act: 1.9498. Min Act: -0.0000

Data Index: 344340 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 2.1066. Min Range: -2.1066

Max Act: 1.8332. Min Act: -0.0000

Data Index: 1191431 (C4 (Web Text))

Max Activating Token Index: 136

Text #4

Max Range: 2.1066. Min Range: -2.1066

Max Act: 1.6608. Min Act: -0.0000

Data Index: 206669 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 2.1066. Min Range: -2.1066

Max Act: 1.6124. Min Act: -0.0000

Data Index: 821132 (C4 (Web Text))

Max Activating Token Index: 380

Text #6

Max Range: 2.1066. Min Range: -2.1066

Max Act: 1.6852. Min Act: -0.0000

Data Index: 1339736 (C4 (Web Text))

Max Activating Token Index: 621

Text #7

Max Range: 2.1066. Min Range: -2.1066

Max Act: 1.7832. Min Act: -0.0000

Data Index: 779288 (C4 (Web Text))

Max Activating Token Index: 786

Text #8

Max Range: 2.1066. Min Range: -2.1066

Max Act: 1.5588. Min Act: -0.0000

Data Index: 1204037 (C4 (Web Text))

Max Activating Token Index: 567

Text #9

Max Range: 2.1066. Min Range: -2.1066

Max Act: 1.6840. Min Act: -0.0000

Data Index: 995886 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 2.1066. Min Range: -2.1066

Max Act: 1.5775. Min Act: -0.0000

Data Index: 839454 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 2.1066. Min Range: -2.1066

Max Act: 1.5719. Min Act: -0.0000

Data Index: 153926 (C4 (Web Text))

Max Activating Token Index: 808

Text #12

Max Range: 2.1066. Min Range: -2.1066

Max Act: 1.5650. Min Act: -0.0000

Data Index: 520373 (C4 (Web Text))

Max Activating Token Index: 436

Text #13

Max Range: 2.1066. Min Range: -2.1066

Max Act: 1.5458. Min Act: -0.0000

Data Index: 1269859 (C4 (Web Text))

Max Activating Token Index: 268

Text #14

Max Range: 2.1066. Min Range: -2.1066

Max Act: 1.5121. Min Act: -0.0000

Data Index: 206494 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 2.1066. Min Range: -2.1066

Max Act: 1.6034. Min Act: -0.0000

Data Index: 335337 (C4 (Web Text))

Max Activating Token Index: 720

Text #16

Max Range: 2.1066. Min Range: -2.1066

Max Act: 1.4796. Min Act: -0.0000

Data Index: 458979 (C4 (Web Text))

Max Activating Token Index: 134

Text #17

Max Range: 2.1066. Min Range: -2.1066

Max Act: 1.4745. Min Act: -0.0000

Data Index: 1353107 (C4 (Web Text))

Max Activating Token Index: 957

Text #18

Max Range: 2.1066. Min Range: -2.1066

Max Act: 1.4271. Min Act: -0.0000

Data Index: 489180 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 2.1066. Min Range: -2.1066

Max Act: 1.4920. Min Act: -0.0000

Data Index: 868563 (C4 (Web Text))

Max Activating Token Index: 20